Hybrid biogeography-based evolutionary algorithms

Hybrid evolutionary algorithms (EAs) are effective optimization methods that combine multiple EAs. We propose several hybrid EAs by combining some recently-developed EAs with a biogeography-based hybridization strategy. We test our hybrid EAs on the continuous optimization benchmarks from the 2013 Congress on Evolutionary Computation (CEC) and on some real-world traveling salesman problems. The new hybrid EAs include two approaches to hybridization: (1) iteration-level hybridization, in which various EAs and BBO are executed in sequence; and (2) algorithm-level hybridization, which runs various EAs independently and then exchanges information between them using ideas from biogeography. Our empirical study shows that the new hybrid EAs significantly outperforms their constituent algorithms with the selected tuning parameters and generation limits, and algorithm-level hybridization is generally better than iteration-level hybridization. Results also show that the best new hybrid algorithm in this paper is competitive with the algorithms from the 2013 CEC competition. In addition, we show that the new hybrid EAs are generally robust to tuning parameters. In summary, the contribution of this paper is the introduction of biogeography-based hybridization strategies to the EA community.